book

Generative AI Foundations in Python

Name: Generative AI Foundations in Python
Author: Carlos Rodriguez
ISBN: 9781835460825

by Carlos Rodriguez

July 2024

Beginner to intermediate

190 pages

5h 30m

English

Packt Publishing

Read now

Unlock full access

Generative AI Foundations in Python
ForewordContributorsAbout the authorAbout the reviewers
Preface
Who this book is forWhat this book coversTo get the most out of this bookDownload the example code filesConventions usedGet in touchShare Your ThoughtsDownload a free PDF copy of this book
Part 1: Foundations of Generative AI and the Evolution of Large Language Models
Chapter 1: Understanding Generative AI: An Introduction
Generative AIDistinguishing generative AI from other AI modelsBriefly surveying generative approachesClarifying misconceptions between discriminative and generative paradigmsChoosing the right paradigmLooking back at the evolution of generative AIOverview of traditional methods in NLPArrival and evolution of transformer-based modelsDevelopment and impact of GPT-4Looking ahead at risks and implicationsIntroducing use cases of generative AIThe future of generative AI applicationsSummaryReferences
Chapter 2: Surveying GenAI Types and Modes: An Overview of GANs, Diffusers, and Transformers
Understanding General Artificial Intelligence (GAI) Types – distinguishing features of GANs, diffusers, and transformersDeconstructing GAI methods – exploring GANs, diffusers, and transformersA closer look at GANsA closer look at diffusion modelsA closer look at generative transformersApplying GAI models – image generation using GANs, diffusers, and transformersWorking with Jupyter Notebook and Google ColabStable diffusion transformerScoring with the CLIP modelSummaryReferences
Chapter 3: Tracing the Foundations of Natural Language Processing and the Impact of the Transformer
Early approaches in NLPAdvent of neural language modelsDistributed representationsTransfer LearningAdvent of NNs in NLPThe emergence of the Transformer in advanced language modelsComponents of the transformer architectureSequence-to-sequence learningEvolving language models – the AR Transformer and its role in GenAIImplementing the original TransformerData loading and preparationTokenizationData tensorizationDataset creationEmbeddings layerPositional encodingMulti-head self-attentionFFNEncoder layerEncoderDecoder layerDecoderComplete transformerTraining functionTranslation functionMain executionSummaryReferences
Chapter 4: Applying Pretrained Generative Models: From Prototype to Production
Prototyping environmentsTransitioning to productionMapping features to production setupSetting up a production-ready environmentLocal development setupVisual Studio CodeProject initializationDocker setupRequirements fileApplication codeCreating a code repositoryCI/CD setupModel selection – choosing the right pretrained generative modelMeeting project objectivesModel size and computational complexityBenchmarkingUpdating the prototyping environmentGPU configurationLoading pretrained models with LangChainSetting up testing dataQuantitative metrics evaluationAlignment with CLIPInterpreting outcomesResponsible AI considerationsAddressing and mitigating biasesTransparency and explainabilityFinal deploymentTesting and monitoringMaintenance and reliabilitySummary
Part 2: Practical Applications of Generative AI
Chapter 5: Fine-Tuning Generative Models for Specific Tasks
Foundation and relevance – an introduction to fine-tuningPEFTLoRAAdaLoRAIn-context learningFine-tuning versus in-context learningPractice project: Fine-tuning for Q&A using PEFTBackground regarding question-answering fine-tuningImplementation in PythonEvaluation of resultsSummaryReferences
Chapter 6: Understanding Domain Adaptation for Large Language Models
Demystifying domain adaptation – understanding its history and importancePractice project: Transfer learning for the finance domainTraining methodologies for financial domain adaptationEvaluation and outcome analysis – the ROUGE metricSummaryReferences

Chapter 7: Mastering the Fundamentals of Prompt Engineering
The shift to prompt-based approachesBasic prompting – guiding principles, types, and structuresGuiding principles for model interactionPrompt elements and structureElevating prompts – iteration and influencing model behaviorsLLMs respond to emotional cuesEffect of personasSituational prompting or role-playAdvanced prompting in action – few-shot learning and prompt chainingPractice project: Implementing RAG with LlamaIndex using PythonSummaryReferences
Chapter 8: Addressing Ethical Considerations and Charting a Path Toward Trustworthy Generative AI
Ethical norms and values in the context of generative AIInvestigating and minimizing bias in generative LLMs and generative image modelsConstrained generation and eliciting trustworthy outcomesConstrained generation with fine-tuningConstrained generation through prompt engineeringUnderstanding jailbreaking and harmful behaviorsPractice project: Minimizing harmful behaviors with filteringSummaryReferences
Index
Why subscribe?
Other Books You May EnjoyPackt is searching for authors like youShare Your ThoughtsDownload a free PDF copy of this book

Content preview from Generative AI Foundations in Python

5 Fine-Tuning Generative Models for Specific Tasks

In our narrative with StyleSprint, we described using a pre-trained generative AI model for creating engaging product descriptions. While this model showed adeptness in generating diverse content, StyleSprint’s evolving needs require a shift in focus. The new challenge is not just about producing content but also about engaging in specific, task-oriented interactions such as automatically answering customer’s specific questions about the products described.

In this chapter, we introduce the concept of fine-tuning, a vital step in adapting a pre-trained model to perform specific downstream tasks. For StyleSprint, this means transforming the model from a versatile content generator to a specialized ...

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.

Read now

Unlock full access

More than 5,000 organizations count on O’Reilly

O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.

Julian F.

Head of Cybersecurity

I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.

Addison B.

Field Engineer

I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.

Amir M.

Data Platform Tech Lead

I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.

Mark W.

Embedded Software Engineer

Publisher Resources

ISBN: 9781835460825

Cloud Computing

Data Engineering

Data Science

AI & ML

Programming Languages

Software Architecture

IT/Ops

Security

Design

Business

Soft Skills

Generative AI Foundations in Python

by Carlos Rodriguez

5

Fine-Tuning Generative Models for Specific Tasks

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.